CN112213313A - Comprehensive positioning method for contact net detection system - Google Patents
Comprehensive positioning method for contact net detection system Download PDFInfo
- Publication number
- CN112213313A CN112213313A CN201910626315.XA CN201910626315A CN112213313A CN 112213313 A CN112213313 A CN 112213313A CN 201910626315 A CN201910626315 A CN 201910626315A CN 112213313 A CN112213313 A CN 112213313A
- Authority
- CN
- China
- Prior art keywords
- positioning
- data
- image
- scanning
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a comprehensive positioning method of a contact net detection system, and relates to the technical field of contact net detection. The method comprises a vehicle positioning step, an image acquisition step, an acquisition end scanning detection step and a back end processing step, wherein the vehicle positioning step realizes the positioning of the vehicle through satellite positioning, when no satellite positioning signal exists, the current position information is determined through the last satellite positioning information before the satellite-free positioning, the vehicle speed information and the time of the satellite-free positioning signal, and the measured positioning information data is verified and calibrated through the pole number information obtained through the back end processing, so that the accurate vehicle positioning data is obtained. The method can realize on-line processing of image data, and is suitable for various domestic rigid contact net suspension types with various operation speeds.
Description
Technical Field
The invention relates to the technical field of contact network detection, in particular to a comprehensive positioning method of a contact network detection system.
Background
The overhead contact system is a high-voltage power transmission line which is erected along a zigzag shape above a steel rail and used for a pantograph to draw current in an electrified railway. The overhead contact system is a main framework of the railway electrification engineering and is a special power transmission line which is erected along a railway line and supplies power to rail vehicles.
The rail transit train is at the in-process of operation, through the working condition of contact net detecting system real-time detection contact net, when the contact net appears unusually, contact net detecting system can combine this unusual condition to generate a defect alarm data with rail transit vehicle position data and time information to send to contact net data center, so that managers manage and maintain. Positioning information obtained by a contact network detection system is an important index for reporting abnormal data of a contact network, the working state of the positioning information directly influences the accuracy of the position of an abnormal point, and if the position data of a rail transit vehicle is inaccurate, a manager cannot obtain accurate positioning information, so that many problems are brought to the aspects of maintenance, management and the like.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a comprehensive positioning method of a contact net detection system, aims to solve the problem of inaccurate detection and positioning of a contact net in the prior art, and provides the positioning method of the contact net detection system.
In order to solve the problems existing in the prior art, the method is realized by the following technical scheme:
the comprehensive positioning method of the contact net detection system is characterized in that: the method comprises the following steps:
positioning the rail transit vehicle: when the satellite positioning unit acquires satellite positioning data, the satellite positioning unit receives the positioning data of the satellite in real time and transmits the positioning data to the positioning control unit; the positioning control unit outputs real-time position data information of the rail transit vehicle in real time, when the satellite positioning unit cannot acquire satellite positioning data, the positioning control unit calculates current positioning information according to the last satellite positioning data before the satellite positioning unit cannot acquire the satellite positioning data, the time difference from the time when the satellite positioning data cannot be acquired to the current time and the speed data of the rail transit vehicle in the time difference, and outputs the calculated current positioning information;
an image acquisition step: when the rail transit vehicle runs, acquiring images of a contact network by using a binocular vision camera, and storing the images acquired by the binocular vision camera into corresponding storage folders;
scanning and detecting at the acquisition end: polling by a scanning unit to check whether new picture data are written into a storage folder in the picture acquisition step, if the new data are written, associating the newly written image data together according to the image data of each part, and writing the associated image data of each part into a data table of a database;
a back-end processing step: firstly, scanning a trigger bar number currently processed by each line in a data table written in a database in the scanning detection step of the acquisition end by a processing unit, reading the storage positions and the reading sequence of a plurality of pictures of each type of algorithm from each data table from the trigger bar number, and then reading data; and deleting a record from the table every time one datum is read in, and updating the currently processed trigger lever number and the positioning data information of the currently processed trigger lever number obtained in the step of positioning the rail transit vehicle.
In the image acquisition step, the images of the contact network acquired by the binocular vision camera are respectively stored according to lines, and the stored lines are displayed in a human-computer interaction interface; in the step of scanning and detecting the acquisition section, a plurality of fixed lines or all lines are limited and scanned through a human-computer interaction interface; when all lines are selected to be scanned, the scanning unit checks whether the lines which are not scanned exist or not, checks whether the lines contain the keywords of a pole number, a wrist arm and a wire clamp or not, checks the maximum trigger pole number of each subfolder under the current line, checks whether the line and the maximum trigger pole number recorded last time change or not, checks the pole numbers one by one, puts picture files under each camera directory into a database according to the keywords until traversal is completed; when one or more lines are selected, timing scanning is carried out according to the line list, and the scanning process is the same as that of the above; the scanning unit regularly scans according to the set polling time until the scanning is stopped from the outside; the back-end processing step comprises two threads, one thread realizes the timing scanning of the data table to be processed, when the data detected in the acquisition end scanning detection step is found, the data is recorded and added into a receiving buffer area, the other thread is in a dormant state at ordinary times, the thread is waken up when the data exists in the receiving buffer area, an algorithm is called for processing, if the defect is found, the defect is written into the data table of the defect database, the dormant state is recovered, and the next waken-up is waited.
A plurality of MDB tables are arranged under each line, and the MDB tables internally comprise detection defect numbers, trigger bar numbers, line names, current time and picture numbers.
And the scanning data table in the acquisition end scanning detection step comprises a line name and a trigger lever number scanned last time.
The algorithm comprises an edge detection algorithm, a straight line extraction algorithm, a morphological analysis algorithm, an image binarization algorithm and an image matching algorithm.
In the back-end processing step, the character recognition of the rod number comprises rod number positioning, rod number character segmentation and rod number character recognition, and the rod number positioning adopts an opencv open source library to obtain the position of the rod number in the image; after the pole number character area image is obtained through pole number positioning, the character string in the pole number image is further divided into independent characters, and the divided characters are identified to obtain the pole number.
After the pole number area image is obtained, whether the pole number belongs to a vertical pole number or a horizontal pole number is judged, if the pole number belongs to the vertical pole number, Canny edge detection processing is carried out on the pole number area image, straight line detection processing is adopted after the processing, the image after the straight line detection processing is rotated, and image reverse processing is carried out on the rotated image; if the bar number belongs to the transverse bar number, directly carrying out image reverse color processing on the bar number image; the method comprises the steps of performing morphological processing, self-adaptive binarization processing, connected domain analysis processing and character filtering on a bar number image after image reverse color processing to obtain an optimal character string area, searching characters in the optimal character string area, performing matching segmentation on the characters to obtain characters, performing feature extraction on single characters, classifying the extracted character features by adopting an algorithm of the character features to obtain bar number information, and finally transmitting the bar number information to a database to update corresponding data in the database.
After the pole number information is obtained, the position information of the pole number is called from the database according to the pole number information, the position information is compared with the positioning data information of the pole number obtained in the step of positioning the rail transit vehicle, and the positioning data information is corrected by combining the comparison result with the line information.
Compared with the prior art, the beneficial technical effects brought by the invention are as follows:
1. the invention provides a general detection positioning method of a contact network, which is used for carrying out intelligent data analysis on video image data of a rigid contact network, carrying out positioning identification on anchor section joint points, automatically dividing an anchor section area, accurately positioning a suspension and support device of the rigid contact network, realizing online processing of the image data and being suitable for suspension types of the rigid contact network with various operation speeds in China.
2. According to the overhead line system and the component positioning method, accurate current vehicle position information can be obtained under the condition of no satellite positioning, the current positioning information is calculated according to the last satellite positioning data before the satellite positioning data cannot be acquired by the satellite positioning unit, the time difference from the time when the satellite positioning data cannot be acquired to the current time and the speed data of the rail transit vehicle in the time difference, and then the position information is compared according to the pole number information acquired in the image acquisition system, so that the measured position information is calibrated, and the accuracy of the vehicle positioning information is ensured.
3. The invention utilizes the database and the network, can combine the resources of a plurality of computers to realize the inquiry of the collected pictures, processes the parallel processing algorithm module of the computer and realizes the process that the user shoots the pictures and checks the operation result. The invention is composed of modules such as an acquisition unit, a scanning unit, a database processing unit, an algorithm processing unit and the like. The acquisition unit is a binocular vision camera and is used for acquiring image data of a contact network, the scanning unit is used for acquiring and checking a new line, inquiring whether a folder is a line according to keywords, inquiring a camera folder according to naming standards, checking all picture files with the same trigger bar number according to the maximum trigger bar number in all current cameras, and warehousing the related picture file names in a unified mode according to the keywords contained in the cameras. And the database processing unit comprises the operations of establishing a database for each line, dynamically generating a data table according to the keywords, writing the data table into the database, avoiding repeated warehousing updating and checking operations, reading the database according to the processed pole number and the currently written maximum pole number and the like. And the processing unit comprises a buffer area, a thread pool, an algorithm processing unit module, different defect classification operations, processing table record deletion operations, output result writing-in output database operations, bar number information file reading and warehousing operations.
4. According to the invention, the pole number information is automatically identified, so that manpower and material resources can be saved, the fault location can be quickly positioned through the pole number information when the railway contact network has a fault, and the method has very important significance for ensuring the normal operation of the train.
5. In the pole number identification process, the acquired images come from different cameras, so that the pole number images acquired by each camera may have both longitudinal pole number images and transverse pole number images, and meanwhile, pole number images in different areas have larger differences. If the same set of configuration parameters is adopted for all the pole number images, the performance of pole number identification can be seriously affected by double images. Therefore, the variable parameters in the program are directly read in the form of configuration files when the program starts to run, so that the optimization processing of images acquired by different cameras, rod number images of different types and rod number images of different areas is facilitated, and the rod number character recognition rate is greatly improved.
Detailed Description
Example 1
As a preferred embodiment of the present invention, the present embodiment discloses:
the comprehensive positioning method of the contact net detection system comprises the following steps:
positioning the rail transit vehicle: when the satellite positioning unit acquires satellite positioning data, the satellite positioning unit receives the positioning data of the satellite in real time and transmits the positioning data to the positioning control unit; the positioning control unit outputs real-time position data information of the rail transit vehicle in real time, when the satellite positioning unit cannot acquire satellite positioning data, the positioning control unit calculates current positioning information according to the last satellite positioning data before the satellite positioning unit cannot acquire the satellite positioning data, the time difference from the time when the satellite positioning data cannot be acquired to the current time and the speed data of the rail transit vehicle in the time difference, and outputs the calculated current positioning information;
an image acquisition step: when the rail transit vehicle runs, acquiring images of a contact network by using a binocular vision camera, and storing the images acquired by the binocular vision camera into corresponding storage folders;
scanning and detecting at the acquisition end: polling by a scanning unit to check whether new picture data are written into a storage folder in the picture acquisition step, if the new data are written, associating the newly written image data together according to the image data of each part, and writing the associated image data of each part into a data table of a database;
a back-end processing step: firstly, scanning a trigger bar number currently processed by each line in a data table written in a database in the scanning detection step of the acquisition end by a processing unit, reading the storage positions and the reading sequence of a plurality of pictures of each type of algorithm from each data table from the trigger bar number, and then reading data; and deleting a record from the table every time one datum is read in, and updating the currently processed trigger lever number and the positioning data information of the currently processed trigger lever number obtained in the step of positioning the rail transit vehicle.
Example 2
As another preferred embodiment of the present invention, the present embodiment discloses:
the comprehensive positioning method of the contact net detection system comprises the following steps:
positioning the rail transit vehicle: when the satellite positioning unit acquires satellite positioning data, the satellite positioning unit receives the positioning data of the satellite in real time and transmits the positioning data to the positioning control unit; the positioning control unit outputs real-time position data information of the rail transit vehicle in real time, when the satellite positioning unit cannot acquire satellite positioning data, the positioning control unit calculates current positioning information according to the last satellite positioning data before the satellite positioning unit cannot acquire the satellite positioning data, the time difference from the time when the satellite positioning data cannot be acquired to the current time and the speed data of the rail transit vehicle in the time difference, and outputs the calculated current positioning information;
an image acquisition step: when the rail transit vehicle runs, acquiring images of a contact network by using a binocular vision camera, and storing the images acquired by the binocular vision camera into corresponding storage folders;
scanning and detecting at the acquisition end: polling by a scanning unit to check whether new picture data are written into a storage folder in the picture acquisition step, if the new data are written, associating the newly written image data together according to the image data of each part, and writing the associated image data of each part into a data table of a database;
a back-end processing step: firstly, scanning a trigger bar number currently processed by each line in a data table written in a database in the scanning detection step of the acquisition end by a processing unit, reading the storage positions and the reading sequence of a plurality of pictures of each type of algorithm from each data table from the trigger bar number, and then reading data; and deleting a record from the table every time one datum is read in, and updating the currently processed trigger lever number and the positioning data information of the currently processed trigger lever number obtained in the step of positioning the rail transit vehicle.
In the image acquisition step, the images of the contact network acquired by the binocular vision camera are respectively stored according to lines, and the stored lines are displayed in a human-computer interaction interface; in the step of scanning and detecting the acquisition section, a plurality of fixed lines or all lines are limited and scanned through a human-computer interaction interface; when all lines are selected to be scanned, the scanning unit checks whether the lines which are not scanned exist or not, checks whether the lines contain the keywords of a pole number, a wrist arm and a wire clamp or not, checks the maximum trigger pole number of each subfolder under the current line, checks whether the line and the maximum trigger pole number recorded last time change or not, checks the pole numbers one by one, puts picture files under each camera directory into a database according to the keywords until traversal is completed; when one or more lines are selected, timing scanning is carried out according to the line list, and the scanning process is the same as that of the above; the scanning unit regularly scans according to the set polling time until the scanning is stopped from the outside; the back-end processing step comprises two threads, one thread realizes the timing scanning of the data table to be processed, when the data detected in the acquisition end scanning detection step is found, the data is recorded and added into a receiving buffer area, the other thread is in a dormant state at ordinary times, the thread is waken up when the data exists in the receiving buffer area, an algorithm is called for processing, if the defect is found, the defect is written into the data table of the defect database, the dormant state is recovered, and the next waken-up is waited. A plurality of MDB tables are arranged under each line, and the MDB tables internally comprise detection defect numbers, trigger bar numbers, line names, current time and picture numbers. And the scanning data table in the acquisition end scanning detection step comprises a line name and a trigger lever number scanned last time.
Example 3
As another preferred embodiment of the present invention, the present embodiment discloses:
the comprehensive positioning method of the contact net detection system comprises the following steps: positioning the rail transit vehicle: when the satellite positioning unit acquires satellite positioning data, the satellite positioning unit receives the positioning data of the satellite in real time and transmits the positioning data to the positioning control unit; the positioning control unit outputs real-time position data information of the rail transit vehicle in real time, when the satellite positioning unit cannot acquire satellite positioning data, the positioning control unit calculates current positioning information according to the last satellite positioning data before the satellite positioning unit cannot acquire the satellite positioning data, the time difference from the time when the satellite positioning data cannot be acquired to the current time and the speed data of the rail transit vehicle in the time difference, and outputs the calculated current positioning information; an image acquisition step: when the rail transit vehicle runs, acquiring images of a contact network by using a binocular vision camera, and storing the images acquired by the binocular vision camera into corresponding storage folders; scanning and detecting at the acquisition end: polling by a scanning unit to check whether new picture data are written into a storage folder in the picture acquisition step, if the new data are written, associating the newly written image data together according to the image data of each part, and writing the associated image data of each part into a data table of a database; a back-end processing step: firstly, scanning a trigger bar number currently processed by each line in a data table written in a database in the scanning detection step of the acquisition end by a processing unit, reading the storage positions and the reading sequence of a plurality of pictures of each type of algorithm from each data table from the trigger bar number, and then reading data; deleting a record from the table every time one datum is read in, and updating the currently processed trigger lever number and the positioning data information of the currently processed trigger lever number obtained in the rail transit vehicle positioning step;
in the image acquisition step, the images of the contact network acquired by the binocular vision camera are respectively stored according to lines, and the stored lines are displayed in a human-computer interaction interface; in the step of scanning and detecting the acquisition section, a plurality of fixed lines or all lines are limited and scanned through a human-computer interaction interface; when all lines are selected to be scanned, the scanning unit checks whether the lines which are not scanned exist or not, checks whether the lines contain the keywords of a pole number, a wrist arm and a wire clamp or not, checks the maximum trigger pole number of each subfolder under the current line, checks whether the line and the maximum trigger pole number recorded last time change or not, checks the pole numbers one by one, puts picture files under each camera directory into a database according to the keywords until traversal is completed; when one or more lines are selected, timing scanning is carried out according to the line list, and the scanning process is the same as that of the above; the scanning unit regularly scans according to the set polling time until the scanning is stopped from the outside; the back-end processing step comprises two threads, one thread realizes the timing scanning of the data table to be processed, when the data detected in the acquisition end scanning detection step is found, the data is recorded and added into a receiving buffer area, the other thread is in a dormant state at ordinary times, the thread is waken up when the data exists in the receiving buffer area, an algorithm is called for processing, if the defect is found, the defect is written into the data table of the defect database, the dormant state is recovered, and the next waken-up is waited. A plurality of MDB tables are arranged under each line, and the MDB tables internally comprise detection defect numbers, trigger bar numbers, line names, current time and picture numbers.
And the scanning data table in the acquisition end scanning detection step comprises a line name and a trigger lever number scanned last time. The algorithm comprises an edge detection algorithm, a straight line extraction algorithm, a morphological analysis algorithm, an image binarization algorithm and an image matching algorithm. In the back-end processing step, the character recognition of the rod number comprises rod number positioning, rod number character segmentation and rod number character recognition, and the rod number positioning adopts an opencv open source library to obtain the position of the rod number in the image; after the pole number character area image is obtained through pole number positioning, the character string in the pole number image is further divided into independent characters, and the divided characters are identified to obtain the pole number.
After the pole number area image is obtained, whether the pole number belongs to a vertical pole number or a horizontal pole number is judged, if the pole number belongs to the vertical pole number, Canny edge detection processing is carried out on the pole number area image, straight line detection processing is adopted after the processing, the image after the straight line detection processing is rotated, and image reverse processing is carried out on the rotated image; if the bar number belongs to the transverse bar number, directly carrying out image reverse color processing on the bar number image; the method comprises the steps of performing morphological processing, self-adaptive binarization processing, connected domain analysis processing and character filtering on a bar number image after image reverse color processing to obtain an optimal character string area, searching characters in the optimal character string area, performing matching segmentation on the characters to obtain characters, performing feature extraction on single characters, classifying the extracted character features by adopting an algorithm of the character features to obtain bar number information, and finally transmitting the bar number information to a database to update corresponding data in the database. After the pole number information is obtained, the position information of the pole number is called from the database according to the pole number information, the position information is compared with the positioning data information of the pole number obtained in the step of positioning the rail transit vehicle, and the positioning data information is corrected by combining the comparison result with the line information.
Claims (8)
1. The comprehensive positioning method of the contact net detection system is characterized in that: the method comprises the following steps:
positioning the rail transit vehicle: when the satellite positioning unit acquires satellite positioning data, the satellite positioning unit receives the positioning data of the satellite in real time and transmits the positioning data to the positioning control unit; the positioning control unit outputs real-time position data information of the rail transit vehicle in real time, when the satellite positioning unit cannot acquire satellite positioning data, the positioning control unit calculates current positioning information according to the last satellite positioning data before the satellite positioning unit cannot acquire the satellite positioning data, the time difference from the time when the satellite positioning data cannot be acquired to the current time and the speed data of the rail transit vehicle in the time difference, and outputs the calculated current positioning information;
an image acquisition step: when the rail transit vehicle runs, acquiring images of a contact network by using a binocular vision camera, and storing the images acquired by the binocular vision camera into corresponding storage folders;
scanning and detecting at the acquisition end: polling by a scanning unit to check whether new picture data are written into a storage folder in the picture acquisition step, if the new data are written, associating the newly written image data together according to the image data of each part, and writing the associated image data of each part into a data table of a database;
a back-end processing step: firstly, scanning a trigger bar number currently processed by each line in a data table written in a database in the scanning detection step of the acquisition end by a processing unit, reading the storage positions and the reading sequence of a plurality of pictures of each type of algorithm from each data table from the trigger bar number, and then reading data; and deleting a record from the table every time one datum is read in, and updating the currently processed trigger lever number and the positioning data information of the currently processed trigger lever number obtained in the step of positioning the rail transit vehicle.
2. The comprehensive positioning method of the catenary detection system as claimed in claim 1, characterized in that: in the image acquisition step, the images of the contact network acquired by the binocular vision camera are respectively stored according to lines, and the stored lines are displayed in a human-computer interaction interface; in the step of scanning and detecting the acquisition section, a plurality of fixed lines or all lines are limited and scanned through a human-computer interaction interface; when all lines are selected to be scanned, the scanning unit checks whether the lines which are not scanned exist or not, checks whether the lines contain the keywords of a pole number, a wrist arm and a wire clamp or not, checks the maximum trigger pole number of each subfolder under the current line, checks whether the line and the maximum trigger pole number recorded last time change or not, checks the pole numbers one by one, puts picture files under each camera directory into a database according to the keywords until traversal is completed; when one or more lines are selected, timing scanning is carried out according to the line list, and the scanning process is the same as that of the above; the scanning unit regularly scans according to the set polling time until the scanning is stopped from the outside; the back-end processing step comprises two threads, one thread realizes the timing scanning of the data table to be processed, when the data detected in the acquisition end scanning detection step is found, the data is recorded and added into a receiving buffer area, the other thread is in a dormant state at ordinary times, the thread is waken up when the data exists in the receiving buffer area, an algorithm is called for processing, if the defect is found, the defect is written into the data table of the defect database, the dormant state is recovered, and the next waken-up is waited.
3. The comprehensive positioning method of the catenary detection system as claimed in claim 2, characterized in that: a plurality of MDB tables are arranged under each line, and the MDB tables internally comprise detection defect numbers, trigger bar numbers, line names, current time and picture numbers.
4. The comprehensive positioning method of the catenary detection system as claimed in claim 2, characterized in that: and the scanning data table in the acquisition end scanning detection step comprises a line name and a trigger lever number scanned last time.
5. The comprehensive positioning method of the overhead line system detection system of claim 1 or 2, characterized in that: the algorithm comprises an edge detection algorithm, a straight line extraction algorithm, a morphological analysis algorithm, an image binarization algorithm and an image matching algorithm.
6. The comprehensive positioning method of the catenary detection system as claimed in claim 1, characterized in that: in the back-end processing step, the character recognition of the rod number comprises rod number positioning, rod number character segmentation and rod number character recognition, and the rod number positioning adopts an opencv open source library to obtain the position of the rod number in the image; after the pole number character area image is obtained through pole number positioning, the character string in the pole number image is further divided into independent characters, and the divided characters are identified to obtain the pole number.
7. The comprehensive positioning method of the catenary detection system as claimed in claim 6, characterized in that: after the pole number area image is obtained, whether the pole number belongs to a vertical pole number or a horizontal pole number is judged, if the pole number belongs to the vertical pole number, Canny edge detection processing is carried out on the pole number area image, straight line detection processing is adopted after the processing, the image after the straight line detection processing is rotated, and image reverse processing is carried out on the rotated image; if the bar number belongs to the transverse bar number, directly carrying out image reverse color processing on the bar number image; the method comprises the steps of performing morphological processing, self-adaptive binarization processing, connected domain analysis processing and character filtering on a bar number image after image reverse color processing to obtain an optimal character string area, searching characters in the optimal character string area, performing matching segmentation on the characters to obtain characters, performing feature extraction on single characters, classifying the extracted character features by adopting an algorithm of the character features to obtain bar number information, and finally transmitting the bar number information to a database to update corresponding data in the database.
8. The comprehensive positioning method of the overhead line system detection system of claim 6 or 7, characterized in that: after the pole number information is obtained, the position information of the pole number is called from the database according to the pole number information, the position information is compared with the positioning data information of the pole number obtained in the step of positioning the rail transit vehicle, and the positioning data information is corrected by combining the comparison result with the line information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910626315.XA CN112213313A (en) | 2019-07-11 | 2019-07-11 | Comprehensive positioning method for contact net detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910626315.XA CN112213313A (en) | 2019-07-11 | 2019-07-11 | Comprehensive positioning method for contact net detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112213313A true CN112213313A (en) | 2021-01-12 |
Family
ID=74047861
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910626315.XA Pending CN112213313A (en) | 2019-07-11 | 2019-07-11 | Comprehensive positioning method for contact net detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112213313A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115994881A (en) * | 2021-10-18 | 2023-04-21 | 合肥中车轨道交通车辆有限公司 | Method and device for detecting defects of overhead line system suspension parts |
-
2019
- 2019-07-11 CN CN201910626315.XA patent/CN112213313A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115994881A (en) * | 2021-10-18 | 2023-04-21 | 合肥中车轨道交通车辆有限公司 | Method and device for detecting defects of overhead line system suspension parts |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101631237B (en) | Video monitoring data storing and managing system | |
| CN103530652B (en) | A kind of video categorization based on face cluster, search method and system thereof | |
| CN113947731B (en) | Foreign matter identification method and system based on contact net safety inspection | |
| CN110290346B (en) | Bidding video acquisition method based on intelligent video analysis | |
| CN102915432A (en) | Method and device for extracting vehicle-bone microcomputer image video data | |
| CN105513083A (en) | PTAM camera tracking method and device | |
| CN107784649A (en) | Plug test remote alarming system and method based on image recognition | |
| US20230343113A1 (en) | Automatic license plate recognition | |
| CN111368824B (en) | Instrument identification method, mobile device and storage medium | |
| CN102968638A (en) | Image sharpness judgment method based on keyword optical character recognition | |
| CN112213313A (en) | Comprehensive positioning method for contact net detection system | |
| CN116989881A (en) | Contact line vibration measurement system and method based on line laser target identification | |
| CN112288675A (en) | Vehicle-mounted contact net component imaging processing method | |
| CN202815869U (en) | Vehicle microcomputer image and video data extraction apparatus | |
| CN116843107B (en) | Building information intelligent management system based on BIM technology | |
| CN107948458A (en) | A kind of vision-based detection control method and system | |
| CN101930593B (en) | Single object image extracting system and method | |
| He et al. | Body condition scoring network based on improved YOLOX | |
| CN115272249B (en) | Defect detection method, device, computer equipment and storage medium | |
| CN114079668B (en) | Information acquisition and arrangement method and system based on internet big data | |
| CN111199168A (en) | Face recognition method based on edge calculation | |
| CN112052729B (en) | Intelligent dynamic high-definition video detection method and system based on face recognition | |
| CN108805903A (en) | A kind of multiple labeling point recognition methods and device based on AR engines | |
| CN115993091B (en) | Contact net pull-out value detection method and device | |
| CN112464724B (en) | Vote identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210112 |